A SIMULATED MODEL OF NEURON CONJUGATION IN AN ARTIFICIAL NEURON NETWORK

Abstract

A simulation model of neuron conjugation in a neural network of a strictly hierar­ch­i­c­al configuration has been developed, which makes it possible to reduce the imitation of the conjugation of neurons in adjacent layers, i.e. shaping the input signal of each layer based on the output signal of the previous layer to a standard matrix multiplication operation. It is shown that the proposed model allows parallelization of the process of simulating the transmission of signals from neurons of each layer to neurons of the next layer, which ma­k­e­s it possible,when using multiprocessor computers, to significantly accelerate the simulation process.